config.cf.default

[DB]
# Connector: mysql
dbCONNECTOR = mysql
dbUSER = 
dbPASS = 
dbSERVER = localhost
#Leave dbSOCKET empty for tcp connection
dbSOCKET = /var/run/mysqld/mysqld.sock

[S2]
#Database name. Needs to be created before executing the sript
dbNAME = db_Pu_S2
data_files = 
#Number or cores for parallel processing
#Set to 0 to deactivate parallel processing
ncpu = 0
#Size of chunks for paper processing and database ingestion
chunksize = 100000

[FIS]
#Database name. Needs to be created before executing the script
dbNAME = db_Pr_FIS
download_folder =
#time to sleep between URL downloads. Increasing facilitates a complete
#download in one execution, at the cost of increasing execution time
ttsleep = 5

[BOE]
dbNAME = db_Law_BOE
xml_dir = data_Law_BOE/XML/
lemas_dir = data_Law_BOE/LEMAS/

[Lemmatizer]
server = http://localhost:7777/en/annotations/
#Online demonstration service
#server = http://librairy.linkeddata.es/nlp/annotations/
stw_file = ./lemmatizer/lemafiles/stopwords/stop-words-english5.txt
dict_eq_file =
POS = "NOUN", "VERB", "ADJECTIVE"
removenumbers = True
#If true, sentence information will be kept, which is necessary when training embedding models
keepSentence = True
#Number of threads that will concurrently send lemmatization requests to the server
concurrent_posts = 10